OpenAICodingReleased 19 January 2026
GPT Audio pricing, context and benchmark
The gpt-audio model is OpenAI's first generally available audio model.
128K
Input context
16K
Output context
$2.5
Official input
$10
Official output
n/a
AA index
01 · Model Overview
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | GPT Audio |
| Model ID | openai/gpt-audio |
| Provider | OpenAI |
| Release date | 19 January 2026 |
| Status | Generally available |
| Input context | 128,000 tokens |
| Output context | 16,384 tokens |
| Official input pricing | $2.5 per 1M tokens |
| Official output pricing | $10 per 1M tokens |
| Cache read pricing | Not published |
| Market input pricing | $2.5 per 1M (cheapest route) |
| Market output pricing | $10 per 1M (cheapest route) |
| Input modalities | text · audio |
| Output modalities | text · audio |
| Reasoning control | Not exposed |
| Tool support | Functions, tool choice, structured outputs |
| Tokenizer | GPT |
| Provider routes | 1 endpoint |
| Artificial Analysis index | Not published |
| Speed | Not published |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $2.5 in |
| Image | no | no | not supported |
| Audio | ✓ yes | ✓ yes | $2.5 in |
| Video | no | no | not supported |
| File (PDF) | no | no | not supported |
02 · Overview
What is GPT Audio?
The gpt-audio model is OpenAI's first generally available audio model.
The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.
Audio is priced...
GPT Audio carries a 128K token window, uses the GPT tokenizer and is served by OpenAI. On Hoodgen it sits in the Coding tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
03 · Release
Release and what changed from the previous version
Released19 January 2026
| Property | GPT Audio Mini | GPT Audio | Change |
|---|---|---|---|
| Released | 2026 | 2026 | Same release window |
| Context | 128K | 128K | Unchanged |
| Max output | 16K | 16K | Unchanged |
| Input price | $0.6 | $2.5 | Higher |
| Output price | $2.4 | $10 | Higher |
| Input modalities | text, audio | text, audio | Unchanged |
| AA index | n/a | n/a | Newer benchmark run |
04 · Capabilities
Features and capabilities
⚙
Function calling
Tools, tool choice and parallel calls, which is what agent loops need to act on results.
{ }
Structured outputs
Schema constrained JSON with response_format, so no parse and retry loop in your code.
♪
Audio and video
Calls, meetings and screen recordings can be summarised in one pass.
⌁
Seeds
A seed can be pinned so the same prompt is reproducible across test runs.
07 · Use cases
What can you do with GPT Audio?
Code generation
New modules, tests and migrations from a written spec.
Refactoring
Cross file renames and API migrations with the whole repo in context.
Code review
Diff review with reasons, not just lint output.
Pairing
In editor loops inside the Hoodgen Coding workspace.
09 · Pricing
GPT Audio pricing
Official pricing
List price
$2.5 / 1M in
$10 / 1M out
- 128K context
- text, audio input
Cheapest route
$2.5 / 1M in
$10 / 1M out
- 1 route on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| OpenAI | standard | $2.5 | $10 | n/a | 100.0% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0650 | $32.50 | 30875 |
| List price | $0.0650 | $32.50 | 30875 |
10 · Developers
API and developer information
| Model ID | openai/gpt-audio |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | frequency_penalty · logit_bias · logprobs · max_tokens · presence_penalty · response_format · seed · stop · structured_outputs · temperature · tool_choice · tools · top_logprobs · top_p |
| Streaming | Yes, server sent events |
| Modality string | text+audio->text+audio |
| Max prompt tokens | 128,000 |
| Max completion tokens | 16,384 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-audio",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'11 · Limitations
Model limitations
| Output cap | 16,384 tokens per request. Long deliverables have to be chunked. |
| Benchmarks not published | Artificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
12 · Comparison
GPT Audio vs other OpenAI models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| GPT Audio | 128K | $2.5 | $10 | n/a | 2026 |
| GPT-5.5 Pro | 1.05M | $30 | $180 | n/a | 2026 |
| GPT-5.4 Pro | 1.05M | $30 | $180 | n/a | 2026 |
| GPT-5.2 Pro | 400K | $21 | $168 | n/a | 2025 |
| o3 Pro | 200K | $20 | $80 | n/a | 2025 |
| GPT-5 Pro | 400K | $15 | $120 | n/a | 2025 |
13 · Privacy
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to OpenAI and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ
GPT Audio questions, answered
GPT Audio is a coding model from OpenAI, released 19 January 2026. The gpt-audio model is OpenAI's first generally available audio model.
✦
Start chatting with GPT Audio
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.